© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 36204
    Prev
    Next
    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Euro
    -0.07
     май
    -0.07
     Repair
    -0.07
     Error
    -0.07
     niž
    -0.07
     salvage
    -0.07
    نامه
    -0.06
    izont
    -0.06
    liž
    -0.06
    ised
    -0.06
    POSITIVE LOGITS
     both
    0.20
     Both
    0.17
    Both
    0.16
    both
    0.15
     BOTH
    0.12
     booth
    0.08
     all
    0.08
    :both
    0.07
     ambos
    0.07
     each
    0.07
    Activations Density 0.046%

    No Known Activations